zilliztech/claude-context Instruction Manual

What zilliztech/claude-context is—in plain language

Vector-backed semantic code search that indexes repositories and retrieves relevant code via MCP for Claude Code, Codex, Gemini, Cursor and others.

Mental model: This repository provides a directly runnable command or package. You give the command an input, it performs the documented workflow, and it returns files, terminal output, a local interface, or a remote result.

InterfacesMCP, library, VS Code

Primary languageNone documented

Typical useReduce repeated directory exploration/context cost on large codebases with semantic retrieval.

Your first 15 minutes

Complete the linked Installation Guide and its verification step.
Create a disposable test folder or use non-sensitive sample data.
Run the small example below and observe what files, ports, or prompts appear.
Read the result before approving writes, network calls, account access, or costs.
Only then repeat the workflow with a real project.

Starter workflow

# IMPORTANT: the top-level key is `mcp_servers` rather than `mcpServers`.
[mcp_servers.claude-context]
command = "npx"
args = ["@zilliz/claude-context-mcp@latest"]
env = { "OPENAI_API_KEY" = "your-openai-api-key", "MILVUS_TOKEN" = "your-zilliz-cloud-api-key" }
# Optional: override the default 10s startup timeout
startup_timeout_ms = 20000

Open Installation Guide Open upstream README

Complete indexed functionality map

Each card below corresponds to a component identified in the repository research. Open a component record for its path, purpose, capabilities, dependencies, risks, and relationships.

Core

library

Index/search code.

README.md

Open component record →

MCP server

mcp_server

Expose search to MCP clients.

README.md

Open component record →

VS Code extension

plugin

IDE semantic search.

README.md

Open component record →

Upstream feature-by-feature guide

These capabilities are derived from the current first-party README and supporting documentation. Names follow upstream terminology so you can search the source documentation precisely.

Upstream capability

Your entire codebase as Claude's context

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns your entire codebase as claude's context. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

🚀 Demo

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns 🚀 demo. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Configure MCP for Claude Code

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns configure mcp for claude code. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Other MCP Client Configurations

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns other mcp client configurations. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Usage in Your Codebase

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns usage in your codebase. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Environment Variables Configuration

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns environment variables configuration. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Using Different Embedding Models

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns using different embedding models. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

File Inclusion & Exclusion Rules

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns file inclusion & exclusion rules. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Available Tools

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns available tools. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

📊 Evaluation

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns 📊 evaluation. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

🔧 Implementation Details

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns 🔧 implementation details. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

Upstream capability

Core Components

Upstream treats this as a distinct part of zilliztech/claude-context. In plain language, use this area when your task concerns core components. Begin with the documented default, test it on disposable input, and open the source section for its current options and limitations.

How to use the main workflows

Choose the smallest relevant function

Start with one capability card instead of asking the repository to do everything at once. This makes permissions, inputs, and output easier to understand.

Prepare a disposable input

Use a sample URL, copied repository, test document, or sandbox account. Keep production credentials and irreplaceable files out of the first run.

Run, observe, and stop

Watch Terminal output or the host application's activity view. If the behavior differs from the README, stop with Control + C or cancel inside the host before retrying.

Inspect the result

Check generated files, diffs, API responses, logs, or previews. Never assume “command finished” means the result is correct.

Save a repeatable recipe

Record the working command and non-secret configuration in your project's README. Store secrets in the documented environment file or password manager.

Copy-paste recipes from upstream documentation

These examples are selected from the repository's first-party documentation. Replace obvious placeholders, keep quotation marks intact, and run them only in the context indicated by the surrounding explanation.

Other MCP Client Configurations

# IMPORTANT: the top-level key is `mcp_servers` rather than `mcpServers`.
[mcp_servers.claude-context]
command = "npx"
args = ["@zilliz/claude-context-mcp@latest"]
env = { "OPENAI_API_KEY" = "your-openai-api-key", "MILVUS_TOKEN" = "your-zilliz-cloud-api-key" }
# Optional: override the default 10s startup timeout
startup_timeout_ms = 20000

Optional: override the default 10s startup timeout

{
  "mcpServers": {
    "claude-context": {
      "command": "npx",
      "args": ["@zilliz/claude-context-mcp@latest"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "MILVUS_TOKEN": "your-zilliz-cloud-api-key"
      }
    }
  }
}

Optional: override the default 10s startup timeout

{
  "mcpServers": {
    "claude-context": {
      "command": "npx",
      "args": ["@zilliz/claude-context-mcp@latest"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key",
        "MILVUS_ADDRESS": "your-zilliz-cloud-public-endpoint",
        "MILVUS_TOKEN": "your-zilliz-cloud-api-key"
      }
    }
  }
}

Configuration, accounts, and files

Configuration files

None documented

A configuration file changes behavior without changing source code. Make one change at a time and keep a backup before editing JSON, TOML, YAML, or environment files.

Important directories

None documented

Paths identify where the relevant implementation or generated files live. Paths beginning with ~ are inside your home folder.

Credentials

embedding key, Milvus/Zilliz credentials

Prefer temporary, least-privileged credentials. Never commit .env, tokens, cookies, private keys, or session exports.

External services

Milvus/Zilliz, embedding provider

Check pricing, data retention, rate limits, and account permissions before enabling optional integrations.

Safe operating habits

Use test data first and keep a current backup or Git commit.
Read commands before pasting. A README is useful evidence, not a substitute for judgment.
Review agent-generated file changes with git diff before committing.
Keep local services bound to 127.0.0.1 unless you intentionally secure and expose them.
Do not give plugins or MCP servers broader filesystem, browser, GitHub, or cloud access than their current task requires.
Confirm API costs and model names before running large batches.
Stop and investigate repeated authentication failures instead of pasting a token into multiple places.

Reference and source trail

The manual reflects first-party files checked on August 18, 2026. It explains the indexed repository rather than promising that every optional third-party integration is available or safe.